7 papers
GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt
Mark Russinovich, Yanan Cai, Keegan Hines +3
Safety alignment is only as robust as its weakest failure mode. Despite extensive work on safety post-training, it has been shown that models can be readily unaligned through post-…
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
Blake Bullwinkel, Giorgio Severi, Keegan Hines +3
Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in…
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
Andrew Zhao, Reshmi Ghosh, Vitor Carvalho +4
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on…
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
Erfan Shayegani, Keegan Hines, Yue Dong +6
Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Bl…
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
Blake Bullwinkel, Mark Russinovich, Ahmed Salem +8
Recent research has demonstrated that state-of-the-art LLMs and defenses remain susceptible to multi-turn jailbreak attacks. These attacks require only closed-box model access and…
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi, Yueqi Xie, Bin Zhu +4
The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection a…